Samuel Oliveira Alves 09a88c9ae5 Add MTP decoding support for GLM-4.x MoE (#1270) ...

* wip: port MTP architecture

Ports the Multi-Token Prediction (MTP) architecture to the older `llama.cpp` codebase used by `ikllama`.

Changes include:
- Updating `llama_batch` to support `mtp_params`.
- Modifying `llama_decode_internal` (and `encode`) to handle MTP operations (Warmup, Update, Draft).
- Adding public APIs for MTP state management (`llama_set_draft_input_hidden_state`).
- Adapting the embedding extraction logic to skip MTP update passes.

* Refactors `server_slot` to support generic speculative decoding (MTP or Draft Model).

* core: enable hybrid outputs (logits + embeddings) for MTP support

* fix(mtp): correct KV-cache slot finding for updates

* fix(mtp): persist hidden states to prevent context corruption during drafting

* refactor(mtp): clean unused code

* fix(mtp): update server to new functions name

* fix(mtp): fix graph and save hidden state

* mtp: refactor integration, context params and kv cache search

* mtp: fix hidden state extraction and speculative acceptance flow

* server: fix MTP warmup for long prompts and reset token buffer

* llama: refactor MTP operation state to context parameters

* server: fix n_past calculation in MTP acceptance

* llama: fix mtp enable flags

* speculative: refactor MTP to use common_speculative interface

* context: remove unused signatures

* clip: fix deprecated enum-enum conversion warning

* common: fix format string crash in help message

* context: fix mtp activation logic

2026-02-22 18:14:39 +01:00

..

llama.h

Add MTP decoding support for GLM-4.x MoE (#1270)

2026-02-22 18:14:39 +01:00